Machine Learning for Medical Image Analysis: A Survey

Machine learning techniques have made significant progress in recent years in the field of healthcare by assisting clinicians in treatment interventions, identification, detection along with the classification of a variety of diseases, including Brain Tumors, Breast Cancer, diagnosis of diabetic retinopathy, as well as, more recently in dealing with the COVID-19 pandemic and its associated medical challenges. To that end, medical image processing employs certain strategies and techniques for manipulating images, which include image acquisition, storage, presentation, and transmission. In this paper, we have overviewed several machine learning and deep learning approaches that are commonly utilized for various image processing tasks, such as image segmentation, image detection, image classification, and image compression on different medical imaging modalities, among which are computed tomography (CT), magnetic resonance imaging (MRI), and x-ray radiography. Focusing on supervised learning and deep learning techniques when applied to medical imaging analysis to enhance the performance in different medical applications using a number of algorithms such as CNNs that lead to efficient outcomes in automatic feature extraction and acceleration of the training process in the detection and classification of different diseases. The methods collected in this survey paper and the results are discussed, and the main conclusions are highlighted.